Unverified50% confidenceFactExact time
环境注入是Agent因具备环境交互能力而特有的新型攻击面，攻击者将恶意指令嵌入Agent读取的外部内容中触发执行
1
Sources
50%
Confidence
Long-term
Relevance
7/25/2026
First Seen
Sources
Agent测试全解析：五大核心维度与自动化实战指南
Related Claims
UnverifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.79% similarUnverified提示注入是针对操作型Agent的独特新型攻击向量，恶意网页可通过视觉元素或隐藏文本向Agent注入指令，如何区分真实指令与伪造指令仍是尚未完全解决的开放问题74% similarVerifiedPrompt injection attacks are a serious threat facing local AI Agents, as maliciously crafted content in files processed by the Agent may induce it to execute dangerous operations.73% similarVerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.72% similarVerifiedThe principle of indirect prompt injection is that an attacker disguises malicious instructions as normal data, delivers them to the model through a data source trusted by the agent, and induces the model to interpret the data as instructions and execute them.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/612287API
curl https://kongchang.com/api/v1/knowledge/claims/612287MCP
get_claim(id=612287)